Abstract
This paper presents our approaches for the BioLaySumm 2024 Shared Task. We evaluate two methods for generating lay summaries based on biomedical articles: (1) fine-tuning the Longformer-Encoder-Decoder (LED) model, and (2) zero-shot and few-shot prompting on GPT-4. In the fine-tuning approach, we individually fine-tune the LED model using two datasets: PLOS and eLife. This process is conducted under two different settings: one utilizing 50% of the training dataset, and the other utilizing the entire 100% of the training dataset. We compare the results of both methods with GPT-4 in zero-shot and few-shot prompting. The experiment results demonstrate that fine-tuning with 100% of the training data achieves better performance than prompting with GPT-4. However, under data scarcity circumstances, prompting GPT-4 seems to be a better solution.- Anthology ID:
- 2024.bionlp-1.67
- Volume:
- Proceedings of the 23rd Workshop on Biomedical Natural Language Processing
- Month:
- August
- Year:
- 2024
- Address:
- Bangkok, Thailand
- Editors:
- Dina Demner-Fushman, Sophia Ananiadou, Makoto Miwa, Kirk Roberts, Junichi Tsujii
- Venues:
- BioNLP | WS
- SIG:
- SIGBIOMED
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 748–754
- Language:
- URL:
- https://aclanthology.org/2024.bionlp-1.67
- DOI:
- Cite (ACL):
- Huy Quoc To, Ming Liu, and Guangyan Huang. 2024. DeakinNLP at BioLaySumm: Evaluating Fine-tuning Longformer and GPT-4 Prompting for Biomedical Lay Summarization. In Proceedings of the 23rd Workshop on Biomedical Natural Language Processing, pages 748–754, Bangkok, Thailand. Association for Computational Linguistics.
- Cite (Informal):
- DeakinNLP at BioLaySumm: Evaluating Fine-tuning Longformer and GPT-4 Prompting for Biomedical Lay Summarization (To et al., BioNLP-WS 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2024.bionlp-1.67.pdf